Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2390 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.5696. Min Act: -0.0001

Data Index: 179713 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.3289. Min Act: -0.0001

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.3756. Min Act: -0.0001

Data Index: 558119 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.2081. Min Act: -0.0001

Data Index: 153686 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1369. Min Act: -0.0001

Data Index: 1124057 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0218. Min Act: -0.0000

Data Index: 521844 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0439. Min Act: -0.0001

Data Index: 1222487 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9419. Min Act: -0.0001

Data Index: 937594 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1196149 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.8971. Min Act: -0.0001

Data Index: 882800 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9813. Min Act: -0.0001

Data Index: 744968 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9431. Min Act: -0.0001

Data Index: 294732 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.8838. Min Act: -0.0000

Data Index: 733359 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9113. Min Act: -0.0001

Data Index: 1186426 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9822. Min Act: -0.0000

Data Index: 49827 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9233. Min Act: -0.0001

Data Index: 260209 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9265. Min Act: -0.0000

Data Index: 628963 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9961. Min Act: -0.0001

Data Index: 361015 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.8789. Min Act: -0.0001

Data Index: 604478 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9043. Min Act: -0.0001

Data Index: 366053 (C4 (Web Text))

Max Activating Token Index: 454